Octavio Santana Suárez

Integration of an XML electronic dictionary with linguistic tools for natural language processing

This study proposes the codification of lexical information in electronic dictionaries, in accordance with a generic and extendable XML scheme model, and its conjunction with linguistic tools for the processing of natural language. Our approach is different from other similar studies in that we propose XML coding of those items from a dictionary of meanings that are less related to the lexical units. Linguistic information, such as morphology, syllables, phonology, etc., will be included by means of specific linguistic tools. The use of XML as a container for the information allows the use of other XML tools for carrying out searches or for enabling presentation of the information in different resources. This model is particularly important as it combines two parallel paradigms-extendable labelling of documents and computational linguistics-and it is also applicable to other languages. We have included a comparison with the labelling proposal of printed dictionaries carried out by the Text Encoding Initiative (TEI). The proposed design has been validated with a dictionary of more than 145000 accepted meanings.

The Spanish morphology in internet

This Web service tags morpholexically any Spanish word and it gets the corresponding forms starting from a canonical form and from the flexion asked for. In the verbs, it deals with the simple and compound conjugation, the enclitic pronouns, the flexion of the participle like verbal adjective and the diminutive of the gerund. With the nonverbal forms, this web service considers: gender and number, heteronomy for change of sex, superlative degree, adverbiation and the appreciative derivation. In the tag and in the generation the prefixation is taken into account. It allows the manipulation of morpholexical relationships. It offers a global vision of the behavior and productivity of the Spanish words in the principal processes of formation (sufixation, prefixation, parasinthesis, suppression, regression, zero-modification, apocopation, metathesis and others which are unclassifiable and that generate alternative graphical forms). It includes the principal Spanish lexicographic repertoires. It considers 151103 canonical forms that produce more than 4900000 flexioned and derived forms and about 90000 morpholexical relationships are established.

Morphoanalysis of Spanish texts: two applications for web pages

The applications described here follow up the works performed in the recent last years by the Data Structures and Computational Linguistics Group at Las Palmas de Gran Canaria University. These works have been developed about computational Linguistics and, as one of their results, some tools for morphologic identification and generation have been released. This work presents the use of those tools as parts of new applications designed to benefit from the great linguistic information flow from Internet. Two kinds of applications are identified, both according to the interactive grade of the linguistics studies to be done, and two prototypes, named DAWeb and NAWeb, are developed with special attention to their architecture in order to maximize the efficiency of both. Analysis modes include: neologism detection, word use (qualitative and quantitative measurements) and some syntax aspects like lexical collocations or prepositional regimes.

Automatic Classification of Optical Sources Candidates to Be in the post-AGB Stage

As a part of an ongoing program, we have carried out a survey searching for stars in their late stages of evolution (post-Asymptotic Giant Branch; post-AGB stars) by observing low-resolution spectra of about 200 objects, all of which need to be classified in the MK system. We present an intelligent system aimed to classify the spectra of post-AGB stars in the MK system in an automatic and objective way. For the development of the system we have combined signal-processing techniques with knowledge-based systems, which allow us to integrate in a unique system tools for analyzing and classifying stellar spectra. The integration of the processing techniques and the knowledge-based system is performed by means of a relational database, which includes symbolic and numerical information.

Network Analysis Techniques Applied to Dictionaries for Identifying Semantics in Lexical Spanish Collocations

The definitions in dictionaries are a source of information to support the results obtained by the automatic extraction of collocations from a text corpus. Measures of association, which are generally used in this task, are useful tools to extract candidate combinations. However, they do not offer information about other features of the collocations. They do not distinguish whether a combination is categorized as a collocation because of its frequency properties or because of its structural properties. Moreover, they cannot distinguish between lexical collocations and functional collocations with delexicalized elements. In this paper, we use a graph database for representing collocations and relations between words retrieved from dictionaries. We consider relations between lemmas and definiens in dictionary entries as well as relations between two words used to define the same sense of another one. This allows us to use a clustering algorithm and measures of centrality and influence in networks to identify semantic characteristics of combinations. The aim is to enrich the information on the combinatorial restrictions of words based on frequencies obtained by means of corpus linguistic techniques.

Functional Disambiguation Using the Syntactic Structures Algorithm for Each Functional Interpretation for Spanish Language

This paper presents a disambiguation method that diminishes the functional combinations of the words of a sentence taking into account the context in which they appear. This process uses an algorithm which does the syntactic analysis of every functional combination of the sentece. In order to control this analysis, a grammar with restrictions has been developed to model the valid syntactic structures of the Spanish language. The main target of our algorithm is the separation between the disambiguation method and the grammar which governs it.

Generación automática de respuestas en análisis morfológico

This paper is concerned with the problem of obtaining a procedure for the automatic generation of texts, inside a defined domain. In the case of study the domain is composed of sentences which result from a Spanish morphological analysis. One important difficulty in order to develop the automatic generation of texts system is to prepare the input data. In the present work the domain is a group of simple results of morphological analysis in natural language. Input data redundancy has been eliminated from such group, the essential information has been extracted and the logical structure has been obtained. The possibility to say the same in different ways forces to select the lexicon, to observe the context and to reinforce the control by means of selection criteria with the aim of assuring that the obtained text is correct and formal, objective and concise. The main contribution of this work consists in converting the logical structure into a sentence which represente the information in a cohesive, coherent, comprehensible way and with certain style.